Mistral is seeking a Research Engineer for the Latency & Throughput team to push the frontier of LLM inference. You will explore speculative decoding, quantization, and KV compression, turning research ideas into production-ready improvements within our vLLM-based serving stack.
You will work closely with inference engineers and researchers, running rigorous experiments, and contributing to design choices that balance latency gains with model quality.
#J-18808-Ljbffr
The Research Engineer: AI Inference & Latency role at Mistral is now open for applications in Greater London, England, United Kingdom.
The position is based in Greater London, England, United Kingdom.
This opportunity is part of our work in IT & Technology, Engineering.
The advertised compensation is 90.000 - 130.000.
We aim to respond to suitable candidates as soon as possible.
Full responsibilities and requirements are described in the listing above.